Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to elite entities or establishments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renches
    -0.77
     Sections
    -0.74
     chromosomes
    -0.69
    ooks
    -0.68
     Klux
    -0.66
     Reps
    -0.64
     rays
    -0.63
     Scouts
    -0.63
    ottest
    -0.63
     Levels
    -0.62
    POSITIVE LOGITS
     consisting
    0.92
     (>
    0.85
    pour
    0.82
     (<
    0.80
     like
    0.79
    ifier
    0.79
     costing
    0.78
     resembling
    0.76
     akin
    0.76
     involving
    0.76
    Act Density 0.570%

    No Known Activations